| With the rapid development of information technology in recent years,computer technology has been applied to various fields.Computer-aided drug design and machine learning are among the commonly used methods and techniques in chemistry and biology.The purpose of this study is to apply these technologies and develop new strategies,which could provide efficient strategies and tools for researchers in related fields.The first chapter briefly introduces the commonly used methods and techniques of computeraided drug design,as well as the commonly used algorithms and general processes in machine learning.In the second chapter,we designed a strategy to discover new inhibitors for Tg CDPK1 with novel scaffolds based on the combination of 2D/3D-QSAR and scaffold-hopping methods.As a result,10 potential inhibitors within 2 new scaffolds were discovered for Tg CDPK1 with experimentally verified inhibitory activities in the micromole level.The discovery of these inhibitors may contribute to the drug development for toxoplasmosis.Besides,the pipeline which is composed in this work as the combination of QSAR and scaffold-hopping is easy to repeat,which will accelerate the procedure of drug discovery and contribute to the drug repurposing study.In the third chapter,in order to further automate the modelling in computer-aided drug design,ABCModeller,an automatic data mining tool,was developed here,which includes automated functions as data preprocessing,significant feature extraction,classification modelling,model evaluation and prediction.The reliability of this tool has been verified through multiple benchmark data sets.In addition,with the advantage of a user-friendly graphical interface of this tool,users without any programming skills can easily obtain reliable models directly from original data,which can contribute to the development of data mining including but not limited to computer-aided drug design and bioinformatics. |
PDF Full Text Request